Documents and OCR

MiniCPM-OCR

The first MiniCPM model built only for documents: it reads text, tables, formulas, charts and seals, and pulls the needed fields out of papers. Just 1.3B. By the authors' tests, 93.68 on Real5-OmniDocBench (document parsing in real conditions: scans, photos, skewed and recaptured pages) and 54.7 on OCRBench v2. Chinese and English are stated, Russian is not. An auxiliary DSpark model is published for it that speeds up generation: according to the authors processing is 55% faster, and the speed is about 1.5 times that of PaddleOCR-VL-1.6 and 3.6 times that of MinerU2.5 Pro. It runs in vLLM, SGLang, llama.cpp and Ollama, with compressed GGUF, AWQ and GPTQ versions.

Developer
OpenBMB (ModelBest), China
First release
Oct 2026
Latest release
Oct 2026
Sizes
1.3B
License
Commercial use allowedApache 2.0
Russian
Not supported
Ready-made builds
GGUF
Running
Available in OllamaAlso runs without a GPU
Industries
Documents and accounting, Finance, Legal
Deploy on your server Hugging Face GitHub

What it does

  • parsing scans and photos of documents into markup: text, tables, formulas
  • extracting fields from invoices, contracts and forms in Chinese and English
  • fast processing of a document flow on a small server

Where it is used

document workflowaccounting and legalbanking and insurance

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. MiniCPM-OCR 1.0 DSpark (ускоряющая модель)
  2. MiniCPM-OCR 1.0 (1.3B)

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can MiniCPM-OCR be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does MiniCPM-OCR need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does MiniCPM-OCR support Russian?

No. The developer documentation lists the supported languages and Russian is not among them.

Where can I download MiniCPM-OCR and what does it cost?

The MiniCPM-OCR weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Documents and OCRUnlimited-OCRBaidu · ChinaCommercial use allowed

Baidu's OCR model building on DeepSeek-OCR ideas: processes multi-page documents and PDFs in a single pass and outputs structured text. Claimed to be multilingual, but the language list is not published. On October 27 Unlimited-OCR-2 (MIT, about 3.3B) came out: according to the authors it parses documents of unlimited length (the SR-SWA technique), and the MarathonDocBench set for very long documents was published with it.

DetailsDocuments and OCRPaddleOCR-VLBaidu (PaddlePaddle) · ChinaCommercial use allowed

A compact document parsing model from the popular PaddleOCR toolkit. Per the model card it supports 109 languages, including Russian; version 1.6 leads the OmniDocBench benchmark.

DetailsImage + textMiniCPM-VOpenBMB (ModelBest and Tsinghua University) · ChinaCommercial use allowed

Compact vision models that run even on a phone or laptop. Good at reading text in photos and understanding video; version 4.6 is only 1.3B. The fresh 4.7 comes in two sizes, 1B and 35B-A3B, the first MoE model in the family. According to the authors, 35B-A3B runs on an iPhone 17 Pro Max at 13+ tokens per second with 3 GB of memory thanks to their way of loading experts. The figures come from the authors themselves.

Details

Source: huggingface.co/openbmb/MiniCPM-OCR-1.0. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.